Utterance Classification Interface With Timed Selection Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies do not effectively support learning or confirming the classification of utterances, particularly in applications like Parent Child Interaction Therapy (PCIT), where trainers or therapists need to classify utterances without relying on predefined classification results.
Innovation Solution
An information processing apparatus and non-transitory computer readable media that generate display and selection information to facilitate learning and confirmation of utterance classification, utilizing a processor to execute a program that displays options, generates selection information, and determines correspondence between multiple selectors' classifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pre-classified utterance results are provided, then classification accuracy is improved, but learning opportunity is reduced
Solution Approach 1:
The system segments the classification process into two distinct modes: training mode where users perform classification manually to learn, and evaluation mode where pre-classified results are provided for accuracy assessment. This segmentation allows the system to serve dual purposes without compromising either learning opportunity or classification accuracy.
Solution Approach 2:
The system dynamically switches between training mode and evaluation mode based on user input. During training mode, the system provides interactive learning opportunities; during evaluation mode, it provides pre-classified results for accuracy measurement. This dynamic adaptation resolves the contradiction by allowing the system to change its behavior based on the current operational context.
2Ease of operation
If interactive selection tracking is implemented, then learning effectiveness is improved, but system complexity is increased
Solution Approach 1:
The selection tracking mechanism serves multiple functions: it records user choices during training, validates classification accuracy during evaluation, and provides feedback for learning. By making the tracking system multi-functional, the patent reduces the need for separate complex systems for each function, thereby managing complexity while maintaining learning effectiveness.
Solution Approach 2:
The system implements feedback mechanisms that provide real-time information about user performance and classification accuracy. This feedback loop simplifies the learning process by guiding users through mistakes and reinforcing correct classifications, reducing the overall system complexity needed for effective learning compared to systems without feedback.
Data Source
AI summary
An information processing apparatus and a non-transitory computer readable media storing a program are provided to learn classification of utterances by a person or confirm a classification result. According to an aspect of the present invention, provided is an information processing apparatus comprising a processor configured to execute a program so as to: in a display information generation step, generate first display information for displaying a plurality of objects associated with each of options, wherein the option corresponds to type of utterance defined according to conversation information; and in a selection information generation step, generate selection information associated with option corresponding to the selected object and time of the selection each time any of the objects is selected.